INDEX

Explanations

programming-related terminology and concepts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<?,

-0.74

pherals

-0.64

 تانيه

-0.62

Бахар

-0.62

archiviato

-0.62

principalTable

-0.61

},[])

-0.60

zsche

-0.60

"];

-0.58

 autorytatywna

-0.58

POSITIVE LOGITS

StoryboardSegue

0.65

 Administration

0.53

 administration

0.52

 صوتيه

0.51

 EdgeInsets

0.50

 QtCore

0.49

MeasureSpec

0.49

tagext

0.48

AddressBook

0.47

GenerationType

0.47

Activations Density 0.229%

programming-related terminology and concepts

No Comments

No Known Activations